TRUST-Planner: Topology-Guided Robust Trajectory Planner for AAVs With Uncertain Obstacle Spatial-Temporal Avoidance

Despite extensive developments in motion planning of autonomous aerial vehicles (AAVs), existing frameworks face the challenges of local minima in complex dynamic environments, leading to increased collision risks. To address these challenges, we present TRUST-Planner, a topology-guided hierarchical planner for robust spatial-temporal obstacle avoidance. In the frontend, a dynamic enhanced visible probabilistic roadmap (DEV-PRM) is proposed to explore topological paths for global guidance rapidly. The backend utilizes a uniform terminal-free minimum control polynomial (UTF-MINCO) to enable efficient predictive obstacle avoidance and fast computation. Furthermore, an incremental multibranch trajectory management framework is introduced to enable spatial-temporal topological decision-making, while efficiently leveraging historical information to reduce replanning runtime. Simulation results show that TRUST-Planner outperforms baseline competitors, achieving millisecond-level computation, higher success rates, and faster traversal in tested complex environments. Real-world experiments further validate the feasibility and practicality of the proposed method.